AI Body Composition in Lung Cancer Screening: Added Value Beyond Lung Cancer Detection.

Background An artificial intelligence (AI) algorithm has been developed for fully automated body composition assessment of lung cancer screening noncontrast low-dose CT of the chest (LDCT) scans, but the utility of these measurements in disease risk prediction models has not been assessed. Purpose To evaluate the added value of CT-based AI-derived body composition measurements in risk prediction of lung cancer incidence, lung cancer death, cardiovascular disease (CVD) death, and all-cause mortality in the National Lung Screening Trial (NLST). Materials and Methods In this secondary analysis of the NLST, body composition measurements, including area and attenuation attributes of skeletal muscle and subcutaneous adipose tissue, were derived from baseline LDCT examinations by using a previously developed AI algorithm. The added value of these measurements was assessed with sex- and cause-specific Cox proportional hazards models with and without the AI-derived body composition measurements for predicting lung cancer incidence, lung cancer death, CVD death, and all-cause mortality. Models were adjusted for confounding variables including age; body mass index; quantitative emphysema; coronary artery calcification; history of diabetes, heart disease, hypertension, and stroke; and other PLCOM2012 lung cancer risk factors. Goodness-of-fit improvements were assessed with the likelihood ratio test. Results Among 20 768 included participants (median age, 61 years [IQR, 57-65 years]; 12 317 men), 865 were diagnosed with lung cancer and 4180 died during follow-up. Including the AI-derived body composition measurements improved risk prediction for lung cancer death (male participants: χ2 = 23.09, P < .001; female participants: χ2 = 15.04, P = .002), CVD death (males: χ2 = 69.94, P < .001; females: χ2 = 16.60, P < .001), and all-cause mortality (males: χ2 = 248.13, P < .001; females: χ2 = 94.54, P < .001), but not for lung cancer incidence (male participants: χ2 = 2.53, P = .11; female participants: χ2 = 1.73, P = .19). Conclusion The body composition measurements automatically derived from baseline low-dose CT examinations added predictive value for lung cancer death, CVD death, and all-cause death, but not for lung cancer incidence in the NLST. Clinical trial registration no. NCT00047385 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Fintelmann in this issue.

In-hospital cardiac arrest survival before and after the COVID-19 pandemic: Have higher performing hospitals stayed high-performing?

BACKGROUND: Survival for in-hospital cardiac arrest (IHCA) has declined since the COVID-19 pandemic. Because the burden of COVID-19 was uneven throughout the U.S., it remains unknown if top-performer hospitals in IHCA survival have remained top-performers since the pandemic. METHODS: Within Get With The Guidelines®-Resuscitation, we identified hospitals with at least 2 years of registry participation pre-pandemic (2017-2019) and post-pandemic (July 2020-2022) and with at least 20 IHCA cases in both periods. Using multivariable hierarchical models with hospital as a random effect and adjusting for patient and arrest characteristics, we calculated risk-standardized survival rates to discharge (RSSR) for IHCA at each hospital during the pre- and post-pandemic periods. We then assessed the correlation between a hospital's pre-pandemic and post-pandemic RSSR for IHCA, and whether the correlation differed by the proportion of Black or Hispanic IHCA patients at each hospital. RESULTS: A total of 243 hospitals were included, comprising 122,561 IHCAs (pre-pandemic: 57,601; post-pandemic: 64,960). Pre-pandemic, the mean RSSR was 26.8% (SD, 5.2%) whereas the mean RSSR post-pandemic was 21.7% (SD, 5.5%). There was good correlation between a hospital's pre- and post-pandemic RSSR: correlation of 0.55. When hospitals were categorized into tertiles based on the proportion of their IHCA patients who were Black or Hispanic, this correlation remained similar: 0.48, 0.68, and 0.45 (interaction P-value: 0.69) for hospitals in the upper, middle and lower tertiles, respectively. CONCLUSION: Although the COVID-19 pandemic affected the U.S. unevenly, there was good correlation in a hospital's performance for IHCA survival before and after the pandemic, even at hospitals caring for a larger proportion of Black and Hispanic patients. Future studies are needed to understand what characteristics of high-performing hospitals pre-pandemic allowed many to continue to excel in the post-pandemic period.

Walking time to nearest public automated external defibrillator for out-of-hospital cardiac arrest in a major U.S. city.

Background: How frequently out-of-hospital cardiac arrest (OHCA) occurs within a reasonable walking distance to the nearest public automated external defibrillator (AED) has not been well studied. Methods: As Kansas City, Missouri has a comprehensive city-wide public AED registry, we identified adults with an OHCA in Kansas City during 2019-2022 in the Cardiac Arrest Registry to Enhance Survival. Using AED location data from the registry, we computed walking times between OHCAs and the nearest registered AED using the Haversine formula, a mapping algorithm to calculate walking distance in miles from one location to another. Results were stratified by OHCA location (home vs. public) and by whether the patient received bystander cardiopulmonary resuscitation (CPR). Results: Of 1,522 OHCAs, 1,291 (84.8%) occurred at home and 231 (15.2%) in public. Among at-home OHCAs, 634 (49.1%) received bystander CPR and no patients had an AED applied even as 297 (23.0%) were within a 4-minute walk to the closest public AED. Among OHCAs in public, 108 (46.8%) were within a 4-minute walk to the closest public AED. For public OHCAs within a 4-minute walk, bystanders applied an AED in 13 (12.0%) of these cases and in 24.5% (13/53) of those who received bystander CPR. Conclusion: In one U.S. city with a publicly available AED registry, there were no instances in which a bystander accessed a public AED for an OHCA at home. For OHCAs in public, nearly half occurred within a 4-minute walk to the closest AED but bystander use of an AED was low.

Generalizable Approach to Quantifying Guideline-Directed Medical Therapy.

BACKGROUND: Quantifying guideline-directed medical therapy (GDMT) intensity is foundational for improving heart failure (HF) care. Existing measures discount dose intensity or use inconsistent weighting. METHODS: The Kansas City Medical Optimization (KCMO) score is the average of total daily to target dose percentages for eligible GDMT, reflecting the percentage of optimal GDMT prescribed (range, 0-100). In Change the Management of Patients With HF, we computed KCMO, HF collaboratory (0-7), and modified HF Collaboratory (0-100) scores for each patient at baseline and for 1-year change in established GDMT at the time (mineralocorticoid receptor antagonist, ß-blocker, ACE [angiotensin-converting enzyme] inhibitor/angiotensin receptor blocker/angiotensin receptor neprilysin inhibitor). We compared baseline and 1-year change distributions and the coefficient of variation (SD/mean) across scores. RESULTS: Among 4532 patients at baseline, mean KCMO, HF collaboratory, and modified HF Collaboratory scores were 38.8 (SD, 25.7), 3.4 (1.7), and 42.2 (22.2), respectively. The mean 1-year change (n=4061) for KCMO was -1.94 (17.8); HF collaborator, -0.11 (1.32); and modified HF Collaboratory, -1.35 (19.8). KCMO had the highest coefficient of variation (0.66), indicating greater variability around the mean than the HF collaboratory (0.49) and modified HF Collaboratory (0.53) scores, reflecting higher resolution of the variability in GDMT intensity across patients. CONCLUSIONS: KCMO measures GDMT intensity by incorporating dosing and treatment eligibility, provides more granularity than existing methods, is easily interpretable (percentage of ideal GDMT), and can be adapted as performance measures evolve. Further study of its association with outcomes and its usefulness for quality assessment and improvement is needed.

Stratification of Lung Cancer Risk with Thoracic Imaging Phenotypes.

In lung cancer screening, estimation of future lung cancer risk is usually guided by demographics and smoking status. The role of constitutional profiles of human body, a.k.a. body habitus, is increasingly understood to be important, but has not been integrated into risk models. Chest low dose computed tomography (LDCT) is the standard imaging study in lung cancer screening, with the capability to discriminate differences in body composition and organ arrangement in the thorax. We hypothesize that the primary phenotypes identified using lung screening chest LDCT can form a representation of body habitus and add predictive power for lung cancer risk stratification. In this pilot study, we evaluated the feasibility of body habitus image-based phenotyping on a large lung screening LDCT dataset. A thoracic imaging manifold was estimated based on an intensity-based pairwise (dis)similarity metric for pairs of spatial normalized chest LDCT images. We applied the hierarchical clustering method on this manifold to identify the primary phenotypes. Body habitus features of each identified phenotype were evaluated and associated with future lung cancer risk using time-to-event analysis. We evaluated the method on the baseline LDCT scans of 1,200 male subjects sampled from National Lung Screening Trial. Five primary phenotypes were identified, which were associated with highly distinguishable clinical and body habitus features. Time-to-event analysis against future lung cancer incidences showed two of the five identified phenotypes were associated with elevated future lung cancer risks (HR=1.61, 95% CI = [1.08, 2.38], p=0.019; HR=1.67, 95% CI = [0.98, 2.86], p=0.057). These results indicated that it is feasible to capture the body habitus by image-base phenotyping using lung screening LDCT and the learned body habitus representation can potentially add value for future lung cancer risk stratification.

Body composition assessment with limited field-of-view computed tomography: A semantic image extension perspective.

Field-of-view (FOV) tissue truncation beyond the lungs is common in routine lung screening computed tomography (CT). This poses limitations for opportunistic CT-based body composition (BC) assessment as key anatomical structures are missing. Traditionally, extending the FOV of CT is considered as a CT reconstruction problem using limited data. However, this approach relies on the projection domain data which might not be available in application. In this work, we formulate the problem from the semantic image extension perspective which only requires image data as inputs. The proposed two-stage method identifies a new FOV border based on the estimated extent of the complete body and imputes missing tissues in the truncated region. The training samples are simulated using CT slices with complete body in FOV, making the model development self-supervised. We evaluate the validity of the proposed method in automatic BC assessment using lung screening CT with limited FOV. The proposed method effectively restores the missing tissues and reduces BC assessment error introduced by FOV tissue truncation. In the BC assessment for large-scale lung screening CT datasets, this correction improves both the intra-subject consistency and the correlation with anthropometric approximations. The developed method is available at https://github.com/MASILab/S-EFOV.

Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification.

The accuracy of predictive models for solitary pulmonary nodule (SPN) diagnosis can be greatly increased by incorporating repeat imaging and medical context, such as electronic health records (EHRs). However, clinically routine modalities such as imaging and diagnostic codes can be asynchronous and irregularly sampled over different time scales which are obstacles to longitudinal multimodal learning. In this work, we propose a transformer-based multimodal strategy to integrate repeat imaging with longitudinal clinical signatures from routinely collected EHRs for SPN classification. We perform unsupervised disentanglement of latent clinical signatures and leverage time-distance scaled self-attention to jointly learn from clinical signatures expressions and chest computed tomography (CT) scans. Our classifier is pretrained on 2,668 scans from a public dataset and 1,149 subjects with longitudinal chest CTs, billing codes, medications, and laboratory tests from EHRs of our home institution. Evaluation on 227 subjects with challenging SPNs revealed a significant AUC improvement over a longitudinal multimodal baseline (0.824 vs 0.752 AUC), as well as improvements over a single cross-section multimodal scenario (0.809 AUC) and a longitudinal imaging-only scenario (0.741 AUC). This work demonstrates significant advantages with a novel approach for co-learning longitudinal imaging and non-imaging phenotypes with transformers. Code available at https://github.com/MASILab/lmsignatures.

Inference-based correction of multi-site height and weight measurement data in the All of Us research program.

OBJECTIVE: Measurement and data entry of height and weight values are error prone. Aggregation of medical record data from multiple sites creates new challenges prompting the need to identify and correct errant values. We sought to characterize and correct issues with height and weight measurement values within the All of Us (AoU) Research Program. MATERIALS AND METHODS: Using the AoU Researcher Workbench, we assessed site-level measurement value distributions to infer unit types. We also used plausibility checks with exceptions for conditions with possible outlier values, eg obesity, and assessed for excess deviation within individual participant's records. RESULTS: 15.8% of height and 22.4% of weight values had missing unit type information. DISCUSSION: We identified several measurement unit related issues: the use of different units of measure within and between sites, missing units, and incorrect labeling of units. Failure to account for these in patient data repositories may lead to erroneous study results and conclusions. CONCLUSION: Discrepancies in height and weight measurement data may arise from missing or mislabeled units. Using site- and participant-level analyses while accounting for outlier value-associated clinical conditions, we can infer measurement units and apply corrections. These methods are adaptable and expandable within AoU and other data repositories.

Extending the value of routine lung screening CT with quantitative body composition assessment.

Certain body composition phenotypes, like sarcopenia, are well established as predictive markers for post-surgery complications and overall survival of lung cancer patients. However, their association with incidental lung cancer risk in the screening population is still unclear. We study the feasibility of body composition analysis using chest low dose computed tomography (LDCT). A two-stage fully automatic pipeline is developed to assess the cross-sectional area of body composition components including subcutaneous adipose tissue (SAT), muscle, visceral adipose tissue (VAT), and bone on T5, T8 and T10 vertebral levels. The pipeline is developed using 61 cases of the VerSe'20 dataset, 40 annotated cases of NLST, and 851 inhouse screening cases. On a test cohort consisting of 30 cases from the inhouse screening cohort (age 55 - 73, 50% female) and 42 cases of NLST (age 55 - 75, 59.5% female), the pipeline achieves a root mean square error (RMSE) of 7.25 mm (95% CI: [6.61, 7.85]) for the vertebral level identification and mean Dice similarity score (DSC) 0.99 ± 0.02, 0.96 ± 0.03, and 0.95 ± 0.04 for SAT, muscle, and VAT, respectively for body composition segmentation. The pipeline is generalized to the CT arm of the NLST dataset (25,205 subjects, 40.8% female, 1,056 lung cancer incidences). Time-to-event analysis for lung cancer incidence indicates inverse association between measured muscle cross-sectional area and incidental lung cancer risks (p < 0.001 female, p < 0.001 male). In conclusion, automatic body composition analysis using routine lung screening LDCT is feasible.

Intrinsic Evaluation of Contextual and Non-contextual Word Embeddings using Radiology Reports.

Many clinical natural language processing methods rely on non-contextual word embedding (NCWE) or contextual word embedding (CWE) models. Yet, few, if any, intrinsic evaluation benchmarks exist comparing embedding representations against clinician judgment. We developed intrinsic evaluation tasks for embedding models using a corpus of radiology reports: term pair similarity for NCWEs and cloze task accuracy for CWEs. Using surveys, we quantified the agreement between clinician judgment and embedding model representations. We compare embedding models trained on a custom radiology report corpus (RRC), a general corpus, and PubMed and MIMIC-III corpora (P&MC). Cloze task accuracy was equivalent for RRC and P&MC models. For term pair similarity, P&MC-trained NCWEs outperformed all other NCWE models (ρspearman 0.61 vs. 0.27-0.44). Among models trained on RRC, fastText models often outperformed other NCWE models and spherical embeddings provided overly optimistic representations of term pair similarity.

Cancer Risk Estimation Combining Lung Screening CT with Clinical Data Elements.

PURPOSE: To develop a model to estimate lung cancer risk using lung cancer screening CT and clinical data elements (CDEs) without manual reading efforts. MATERIALS AND METHODS: Two screening cohorts were retrospectively studied: the National Lung Screening Trial (NLST; participants enrolled between August 2002 and April 2004) and the Vanderbilt Lung Screening Program (VLSP; participants enrolled between 2015 and 2018). Fivefold cross-validation using the NLST dataset was used for initial development and assessment of the co-learning model using whole CT scans and CDEs. The VLSP dataset was used for external testing of the developed model. Area under the receiver operating characteristic curve (AUC) and area under the precision-recall curve were used to measure the performance of the model. The developed model was compared with published risk-prediction models that used only CDEs or imaging data alone. The Brock model was also included for comparison by imputing missing values for patients without a dominant pulmonary nodule. RESULTS: A total of 23 505 patients from the NLST (mean age, 62 years ± 5 [standard deviation]; 13 838 men, 9667 women) and 147 patients from the VLSP (mean age, 65 years ± 5; 82 men, 65 women) were included. Using cross-validation on the NLST dataset, the AUC of the proposed co-learning model (AUC, 0.88) was higher than the published models predicted with CDEs only (AUC, 0.69; P < .05) and with images only (AUC, 0.86; P < .05). Additionally, using the external VLSP test dataset, the co-learning model had a higher performance than each of the published individual models (AUC, 0.91 [co-learning] vs 0.59 [CDE-only] and 0.88 [image-only]; P < .05 for both comparisons). CONCLUSION: The proposed co-learning predictive model combining chest CT images and CDEs had a higher performance for lung cancer risk prediction than models that contained only CDE or only image data; the proposed model also had a higher performance than the Brock model.Keywords: Computer-aided Diagnosis (CAD), CT, Lung, Thorax Supplemental material is available for this article. © RSNA, 2021.

Development and Characterization of a Chest CT Atlas.

A major goal of lung cancer screening is to identify individuals with particular phenotypes that are associated with high risk of cancer. Identifying relevant phenotypes is complicated by the variation in body position and body composition. In the brain, standardized coordinate systems (e.g., atlases) have enabled separate consideration of local features from gross/global structure. To date, no analogous standard atlas has been presented to enable spatial mapping and harmonization in chest computational tomography (CT). In this paper, we propose a thoracic atlas built upon a large low dose CT (LDCT) database of lung cancer screening program. The study cohort includes 466 male and 387 female subjects with no screening detected malignancy (age 46-79 years, mean 64.9 years). To provide spatial mapping, we optimize a multi-stage inter-subject non-rigid registration pipeline for the entire thoracic space. Briefly, with 50 scans of 50 randomly selected female subjects as fine tuning dataset, we search for the optimal configuration of the non-rigid registration module in a range of adjustable parameters including: registration searching radius, degree of keypoint dispersion, regularization coefficient and similarity patch size, to minimize the registration failure rate approximated by the number of samples with low Dice similarity score (DSC) for lung and body segmentation. We evaluate the optimized pipeline on a separate cohort (100 scans of 50 female and 50 male subjects) relative to two baselines with alternative non-rigid registration module: the same software with default parameters and an alternative software. We achieve a significant improvement in terms of registration success rate based on manual QA. For the entire study cohort, the optimized pipeline achieves a registration success rate of 91.7%. The application validity of the developed atlas is evaluated in terms of discriminative capability for different anatomic phenotypes, including body mass index (BMI), chronic obstructive pulmonary disease (COPD), and coronary artery calcification (CAC).

Automated External Defibrillator Use After Out-of-Hospital Cardiac Arrest at Recreational Facilities.

This cohort study examines bystander automated external defibrillator (AED) application and survival outcomes for out-of-hospital cardiac arrest at recreational facilities in US states with and without AED legislation.